Skip to main content
command CX Codex

create-test-cases — Claude Code command for manual test cases

create-test-cases drafts browser-focused manual test cases in Markdown for a project feature or area. Use it to prepare cases for /qa:manual-test-run.

no license ★ 406 updated 2026-11-01

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/create-test-cases.md
Open on GitHub

What create-test-cases does

The command examines the selected feature and relevant project material, then writes files under docs/living-test-cases/{feature-slug}/. The folder contains a README.md index and separate TC-{NNN}.md files with a test type, priority, prerequisites, actions, and observable expected results.

Cases can cover core flows, error handling, and unusual states. Each action should be clear enough to perform without guessing, and each result should be visible in the browser. The output is Markdown, not test-framework code. If you omit the feature or area, the command asks what to cover; an outcome the browser cannot show may be marked UNSURE by the runner.

What it helps with

  • document manual checks for a feature
  • turn a user flow into explicit test steps
  • record visible expected outcomes in Markdown
  • cover invalid input and unusual states

Example prompts for the agent

  • Write manual test cases for the checkout flow.
  • Create browser checks for the profile page.
  • Draft cases for data import, including invalid input.

How to install create-test-cases

Manually: put the files in place

.claude/commands/create-test-cases.md

Call it with /create-test-cases. For all projects use ~/.claude/commands/

Questions about create-test-cases

How do I install create-test-cases in Claude Code?

Save the command file at .claude/commands/create-test-cases.md.

What does create-test-cases do?

It creates Markdown files for manual checks in docs/living-test-cases/{feature-slug}/, with actions and observable outcomes.

Does the command generate automated test code?

No. It writes Markdown cases for manual browser checks, not specs for Playwright, Jest, or another test framework.

Similar slash commands

All slash commands for Testing and QA →

From the same set26

The whole set →
commit Runs a background subagent to commit staged Git changes following ATLAS conventions. Useful when you want automated commits without blocking your session. CX Codex +1 ★ 406repo stars stage-commit The stage-commit command hands working-directory changes to a background commit subagent. Use it to create grouped commits and keep going until Git reports a clean tree. CX Codex +1 ★ 406repo stars learning-from-mistakes learning-from-mistakes — a skill that writes a bug or mistake into a separate file after the problem is resolved. Captures the cause, fix, and lesson to avoid repeating the debugging work. CX Codex +1 ★ 406repo stars log log inspects recent git commits, summarizes their themes, and maps them against uncommitted changes in your working tree. CX Codex +1 ★ 406repo stars wireframe The wireframe command renders a static low-fidelity screen layout into a single HTML file — gray boxes, dashed borders, no libraries. Opens with a double-click. CX Codex +1 ★ 406repo stars commit Creates Git commits autonomously using ATLAS conventions without asking for approval. Handles staged files or splits working changes into clean commits. CX Codex ★ 406repo stars abstraction-power The abstraction-power skill guides Claude Code from concrete code examples to reusable models by spotting their shared structure. Use it to examine duplicated logic or shape a system design. CX Codex +1 ★ 406repo stars get-to-know get-to-know is a Claude Code command that initializes project context by gathering stack, structure, and conventions, creating a project map, and configuring the environment. CX Codex +1 ★ 406repo stars

Project sponsors

Companies that keep this analytics open